Back to RepoInsider
Signal dossier

opendatalab/MinerU

PythonAI Tools

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Pulse

98

Velocity

+326%

Stars

71,148

Best forAi4ScienceDocument AnalysisDocx

Converts PDFs and Office docs into LLM-ready markdown/JSON for agents.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Instantly convert PDFs and Office docs into LLM-ready markdown/JSON for your agentic workflows.

Why Trending

Essential preprocessing step for RAG and agentic document understanding.

Target Audience

AI developers building agentic workflows.

Similar Projects

LangChainLlamaIndex
RepoInsider · Spot breakout GitHub repos early